Github user adamonduty commented on a diff in the pull request:
https://github.com/apache/incubator-nifi/pull/27#discussion_r24943917
--- Diff:
nifi/nifi-nar-bundles/nifi-standard-bundle/nifi-standard-processors/src/main/java/org/apache/nifi/processors/standard/IdentifyMimeType.java
---
@@ -239,87 +128,39 @@ public void onTrigger(final ProcessContext context,
final ProcessSession session
}
final ProcessorLog logger = getLogger();
- final boolean identifyZip =
context.getProperty(IDENTIFY_ZIP).asBoolean();
- final boolean identifyTar =
context.getProperty(IDENTIFY_TAR).asBoolean();
final ObjectHolder<String> mimeTypeRef = new ObjectHolder<>(null);
+ final ObjectHolder<String> extensionRef = new ObjectHolder<>(null);
session.read(flowFile, new InputStreamCallback() {
@Override
public void process(final InputStream stream) throws
IOException {
try (final InputStream in = new
BufferedInputStream(stream)) {
- // read in up to magicHeaderMaxLength bytes
- in.mark(magicHeaderMaxLength);
- byte[] header = new byte[magicHeaderMaxLength];
- for (int i = 0; i < header.length; i++) {
- final int next = in.read();
- if (next >= 0) {
- header[i] = (byte) next;
- } else if (i == 0) {
- header = new byte[0];
- } else {
- final byte[] newBuffer = new byte[i - 1];
- System.arraycopy(header, 0, newBuffer, 0, i -
1);
- header = newBuffer;
- break;
- }
- }
- in.reset();
-
- for (final MagicHeader magicHeader : magicHeaders) {
- if (magicHeader.matches(header)) {
- mimeTypeRef.set(magicHeader.getMimeType());
- return;
- }
- }
-
- if (!identifyZip) {
- for (final MagicHeader magicHeader :
zipMagicHeaders) {
- if (magicHeader.matches(header)) {
- mimeTypeRef.set(magicHeader.getMimeType());
- return;
- }
- }
- }
-
- if (!identifyTar) {
- for (final MagicHeader magicHeader :
tarMagicHeaders) {
- if (magicHeader.matches(header)) {
- mimeTypeRef.set(magicHeader.getMimeType());
- return;
- }
- }
+ TikaInputStream tikaStream = TikaInputStream.get(in);
+ Metadata metadata = new Metadata();
+ // Get mime type
+ MediaType mediatype = detector.detect(tikaStream,
metadata);
+ mimeTypeRef.set(mediatype.toString());
+ // Get common file extension
+ try {
+ MimeType mimetype;
+ mimetype =
config.getMimeRepository().forName(mediatype.toString());
+ extensionRef.set(mimetype.getExtension());
+ } catch (MimeTypeException ex) {
+ logger.warn("MIME type detection failed: {}", new
Object[]{ex.toString()});
--- End diff --
Didn't know that! I'll fix and re-push.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
